Can I run this LLM?
Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run NVIDIA Nemotron 3.5 Bolt 74B A9B?
Nemotron · See model card · estimated for a 144.0 GB machine at 4K context.
Yes — it runs great.
Best fit: NVIDIA Nemotron 3.5 Bolt 74B A9B at FP16 · 148.2 GB · 65–98 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 28.8 GB | 270–405 tok/s | Runs great |
| Q3_K_M | 39.0 GB | 247–371 tok/s | Runs great |
| Q4_K_M | 50.2 GB | 226–339 tok/s | Runs great |
| Q5_K_M | 58.9 GB | 212–318 tok/s | Runs great |
| Q6_K | 72.4 GB | 194–290 tok/s | Runs great |
| Q8_0 | 78.9 GB | 186–279 tok/s | Runs great |
| FP16 | 148.2 GB | 65–98 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) runsNVIDIA Nemotron 3.5 Bolt 74B A9B on other machinesWhat to buy to run it →
Ran NVIDIA Nemotron 3.5 Bolt 74B A9B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →